At the second stage, another network is trained to synthesize the structure and appearance of hair images from the input sketch and the generated matte.
In this work, we propose SimpModeling, a novel sketch-based system for helping users, especially amateur users, easily model 3D animalmorphic heads - a prevalent kind of heads in character design.
Instead of using a predefined fixed-size local support in voxelization, which potentially limits the access of richer local geometry information, we propose to learn the support size in a data-driven manner.
Experimental results validate the effectiveness of VMNet: specifically, on the challenging ScanNet dataset for large-scale segmentation of indoor scenes, it outperforms the state-of-the-art SparseConvNet and MinkowskiNet (74. 6% vs 72. 5% and 73. 6% in mIoU) with a simpler network structure (17M vs 30M and 38M parameters).
Motion style transfer is an important problem in many computer graphics and computer vision applications, including human animation, games, and robotics.
Removing outlier correspondences is one of the critical steps for successful feature-based point cloud registration.
To handle the incompleteness of objects recovered from videos, we propose a novel scale estimation method that extracts plausible dimensions of objects for scale optimization.
Semantic segmentation and semantic edge detection can be seen as two dual problems with close relationships in computer vision.
Ranked #10 on Semantic Segmentation on S3DIS
Our method essentially uses input sketches as soft constraints and is thus able to produce high-quality face images even from rough and/or incomplete sketches.
In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds.
Ranked #4 on Point Cloud Registration on 3DMatch Benchmark
In this paper, we leverage a 3D fully convolutional network for 3D point clouds, and propose a novel and practical learning mechanism that densely predicts both a detection score and a description feature for each 3D point.
Ranked #2 on Point Cloud Registration on KITTI
We introduce SketchGNN, a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches.
In this paper, we study the problem of multi-view sketch correspondence, where we take as input multiple freehand sketches with different views of the same object and predict as output the semantic correspondence among the sketches.
Being natural, touchless, and fun-embracing, language-based inputs have been demonstrated effective for various tasks from image generation to literacy education for children.
The key enablers of our system are two carefully designed neural networks, namely, S2ONet, which converts an input sketch to a dense 2D hair orientation field; and O2VNet, which maps the 2D orientation field to a 3D vector field.
At the structural level, we train a Structured Parts VAE (SP-VAE), which jointly learns the part structure of a shape collection and the part geometries, ensuring a coherence between global shape structure and surface details.
To bridge the gap between these two spaces in neural networks, we propose a neural line rasterization module to convert the vector sketch along with the attention estimated by RNN into a bitmap image, which is subsequently consumed by CNN.
We introduce LUCSS, a language-based system for interactive col- orization of scene sketches, based on their semantic understanding.
Inspired by the recent advance of image-based object reconstruction using deep learning, we present an active reconstruction model using a guided view planner.
As artists often use their personal color themes in their paintings, making these palettes appear frequently in the dataset, we employed density estimation to capture the characteristics of palette data.